Conor B. Hamill

Senior Data Scientist

NatWest Group

Edinburgh, Scotland

Data scientist/AI researcher working in financial services, based in Edinburgh, Scotland. My interests consist of supervised learning techniques, agent-based modelling, model drift estimation, and human-like abiltiies of large language models, alongside enduring curiosity about astrophysics and quantum computing. Outside data science, I enjoy travelling with my wife, esponiage and thriller novels, comedy podcasts, and cooking.

I graduated from my integrated Master’s in Physics from Queen’s University, Belfast in 2017. My Master’s project consisted of contributing to the development of a laser system for discriminating between chiral molecules, with experiments taking place at Uppsala University.

Following my Master’s, I started my PhD in experimental nuclear astrophysics at the University of Edinburgh. My initial research included being part of the A2 collaboration at the Mainz Microtron MAMI, Germany, with focus on photo-nuclear reactions. I undertook simulations and experimental preparation for the measurement of astrophysical reactions relevant to the production of radioactive nuclei in supernovae at the ISOLDE facility at CERN and a participated in the running of experiments into radioactive isotopes at the CRIB facility, Japan. My main PhD research topic consisted on measuring transfer reactions at TUNL, North Carolina, USA, for nova explosions and the astrophysical weak s-process, which can be read here.

I defended my PhD in 2021 and joined NatWest Group as a data scientist in the Data Science & Innovation team. My work at NatWest has consisted of developing machine learning models across a range of domains in the bank, as well as undertaking AI research for financial services as part of the NatWest AI Research (NAIR) team.

My published research works as a PhD research student and during my time as part of NAIR in NatWest can be found under the publications tab, as well as by following the link to my Google Scholar profile below.

news

Sep 06, 2024	On the 6th September, Raad Khraishi and I will be presenting a talk at ODSC Europe 2024, titled “Simulating Human Behaviour in Financial Contexts: Leveraging AI and Agent-Based Models”, highlighting some of the research being undertaken at NatWest Group.
Aug 21, 2024	Represented NatWest at the careers event of the 2024 Nuclear Physics Summer School in Durham
Aug 02, 2024	A sample of our AI research is highlighted on the NatWest Group website.
Jul 18, 2024	Publication of a review paper I contributed to titled “A Brief Review of Quantum Machine Learning for Financial Services”, as part of a collaboration between the NatWest Group and the University of Edinburgh.

latest posts

Sep 08, 2024	So you want to get into data science?
Jun 18, 2024	What I would tell myself at the start of my PhD
Mar 30, 2024	Visualisation libraries in python for expanding your data storytelling

selected publications

arXiv
A Brief Review of Quantum Machine Learning for Financial Services

Mina Doosti , Petros Wallden , Conor Brian Hamill , and 3 more authors

2024

Abs Bib HTML

This review paper examines state-of-the-art algorithms and techniques in quantum machine learning with potential applications in finance. We discuss QML techniques in supervised learning tasks, such as Quantum Variational Classifiers, Quantum Kernel Estimation, and Quantum Neural Networks (QNNs), along with quantum generative AI techniques like Quantum Transformers and Quantum Graph Neural Networks (QGNNs). The financial applications considered include risk management, credit scoring, fraud detection, and stock price prediction. We also provide an overview of the challenges, potential, and limitations of QML, both in these specific areas and more broadly across the field. We hope that this can serve as a quick guide for data scientists, professionals in the financial sector, and enthusiasts in this area to understand why quantum computing and QML in particular could be interesting to explore in their field of expertise.
@misc{doosti2024briefreviewquantummachine, title = {A Brief Review of Quantum Machine Learning for Financial Services}, author = {Doosti, Mina and Wallden, Petros and Hamill, Conor Brian and Hankache, Robert and Brown, Oliver Thomson and Heunen, Chris}, year = {2024}, eprint = {2407.12618}, archiveprefix = {arXiv}, primaryclass = {quant-ph}, }
arXiv
Agent-based Modelling of Credit Card Promotions

Conor B. Hamill , Raad Khraishi , Simona Gherghel , and 4 more authors

arXiv e-prints, Nov 2023

Abs Bib HTML

Interest-free promotions are a prevalent strategy employed by credit card lenders to attract new customers, yet the research exploring their effects on both consumers and lenders remains relatively sparse. The process of selecting an optimal promotion strategy is intricate, involving the determination of an interest-free period duration and promotion-availability window, all within the context of competing offers, fluctuating market dynamics, and complex consumer behaviour. In this paper, we introduce an agent-based model that facilitates the exploration of various credit card promotions under diverse market scenarios. Our approach, distinct from previous agent-based models, concentrates on optimising promotion strategies and is calibrated using benchmarks from the UK credit card market from 2019 to 2020, with agent properties derived from historical distributions of the UK population from roughly the same period. We validate our model against stylised facts and time-series data, thereby demonstrating the value of this technique for investigating pricing strategies and understanding credit card customer behaviour. Our experiments reveal that, in the absence of competitor promotions, lender profit is maximised by an interest-free duration of approximately 12 months while market share is maximised by offering the longest duration possible. When competitors do not offer promotions, extended promotion availability windows yield maximum profit for lenders while also maximising market share. In the context of concurrent interest-free promotions, we identify that the optimal lender strategy entails offering a more competitive interest-free period and a rapid response to competing promotional offers. Notably, a delay of three months in responding to a rival promotion corresponds to a 2.4% relative decline in income.
@article{2023arXiv231101901H, author = {Hamill, Conor B. and Khraishi, Raad and Gherghel, Simona and Lawrence, Jerrard and Mercuri, Salvatore and Okhrati, Ramin and Cowan, Greig A.}, title = {{Agent-based Modelling of Credit Card Promotions}}, journal = {arXiv e-prints}, keywords = {Computer Science - Multiagent Systems, Economics - General Economics}, year = {2023}, month = nov, eid = {arXiv:2311.01901}, pages = {arXiv:2311.01901}, doi = {10.48550/arXiv.2311.01901}, archiveprefix = {arXiv}, eprint = {2311.01901}, primaryclass = {cs.MA}, adsurl = {https://ui.adsabs.harvard.edu/abs/2023arXiv231101901H}, adsnote = {Provided by the SAO/NASA Astrophysics Data System}, }

EPJA

Study of the 25Mg(d, p)26Mg reaction to constrain the 25Al(p, γ)26Si resonant reaction rates in nova burning conditions

C. B. Hamill , P. J. Woods , D. Kahl , and 5 more authors

The European Physical Journal A, Feb 2020

Bib HTML

@article{Hamill2020,
  title = {Study of the 25Mg(d, p)26Mg reaction to constrain the 25Al(p, ${\gamma }$)26Si resonant reaction rates in nova burning conditions},
  volume = {56},
  issn = {1434-601X},
  url = {http://dx.doi.org/10.1140/epja/s10050-020-00052-9},
  doi = {10.1140/epja/s10050-020-00052-9},
  number = {2},
  journal = {The European Physical Journal A},
  publisher = {Springer Science and Business Media LLC},
  author = {Hamill, C. B. and Woods, P. J. and Kahl, D. and Longland, R. and Greene, J. P. and Marshall, C. and Portillo, F. and Setoodehnia, K.},
  year = {2020},
  month = feb,
  dimensions = {true},
}